Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0151. Min Range: -3.0151

Max Act: 3.0151. Min Act: -0.0000

Data Index: 441766 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.6655. Min Act: -0.0000

Data Index: 383798 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.3582. Min Act: -0.0000

Data Index: 313811 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.3576. Min Act: -0.0000

Data Index: 1365488 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.5989. Min Act: -0.0000

Data Index: 8404 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1456563 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1469333 (Python Code)

Max Activating Token Index: 703

Text #7

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.4382. Min Act: -0.0000

Data Index: 897520 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.4084. Min Act: -0.0000

Data Index: 1395663 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.4030. Min Act: -0.0000

Data Index: 1639833 (Python Code)

Max Activating Token Index: 529

Text #10

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.4019. Min Act: -0.0000

Data Index: 502458 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.2790. Min Act: -0.0000

Data Index: 1420506 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.3302. Min Act: -0.0000

Data Index: 1163116 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.2040. Min Act: -0.0000

Data Index: 1448494 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.3029. Min Act: -0.0000

Data Index: 1385070 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1448122 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.2656. Min Act: -0.0000

Data Index: 1529075 (Python Code)

Max Activating Token Index: 1013

Text #17

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.1496. Min Act: -0.0000

Data Index: 1541899 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.0240. Min Act: -0.0000

Data Index: 1612660 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 3.0151. Min Range: -3.0151

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1649774 (Python Code)

Max Activating Token Index: 820